Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2994 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1326. Min Range: -1.1326
Max Act: 1.1326. Min Act: -0.1700
Data Index: 3353502 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1326. Min Range: -1.1326
Max Act: 1.1326. Min Act: -0.1700
Data Index: 163155 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1326. Min Range: -1.1326
Max Act: 1.1326. Min Act: -0.1700
Data Index: 163153 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1326. Min Range: -1.1326
Max Act: 1.1326. Min Act: -0.1700
Data Index: 163154 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1326. Min Range: -1.1326
Max Act: 1.1150. Min Act: -0.1700
Data Index: 163156 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1326. Min Range: -1.1326
Max Act: 1.0975. Min Act: -0.1700
Data Index: 3353494 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1326. Min Range: -1.1326
Max Act: 1.0800. Min Act: -0.1700
Data Index: 163147 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1326. Min Range: -1.1326
Max Act: 1.0451. Min Act: -0.1700
Data Index: 3353479 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1326. Min Range: -1.1326
Max Act: 1.0276. Min Act: -0.1700
Data Index: 8305841 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1326. Min Range: -1.1326
Max Act: 1.0102. Min Act: -0.1700
Data Index: 3165990 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1326. Min Range: -1.1326
Max Act: 1.0102. Min Act: -0.1700
Data Index: 355374 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1326. Min Range: -1.1326
Max Act: 1.0102. Min Act: -0.1700
Data Index: 8559881 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1326. Min Range: -1.1326
Max Act: 1.0102. Min Act: -0.1700
Data Index: 8357522 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1326. Min Range: -1.1326
Max Act: 1.0102. Min Act: -0.1700
Data Index: 7071337 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1326. Min Range: -1.1326
Max Act: 1.0102. Min Act: -0.1700
Data Index: 3360639 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1326. Min Range: -1.1326
Max Act: 0.9929. Min Act: -0.1700
Data Index: 4595952 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1326. Min Range: -1.1326
Max Act: 0.9929. Min Act: -0.1700
Data Index: 1203128 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1326. Min Range: -1.1326
Max Act: 0.9929. Min Act: -0.1700
Data Index: 1710348 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1326. Min Range: -1.1326
Max Act: 0.9929. Min Act: -0.1700
Data Index: 3522671 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1326. Min Range: -1.1326
Max Act: 0.9929. Min Act: -0.1700
Data Index: 5170563 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19